pdfbeads 1.0.2 → 1.0.3

data/ChangeLog

@@ -5,3 +5,16 @@
 2010 November 12 (Alexey Kryukov) Version 1.0.1
 
     * JBIG2 support didn't work properly under MS Windows.
+
+2010 November 15 (Alexey Kryukov) Version 1.0.3
+
+    + Make it possible to specify binarization threshold for mixed scans
+      (it is still not recommended to perform segmentation with pdfbeads,
+      unless the image has been previously processed with ScanTailor, so
+      the normal value for this parameter is 1).
+
+    * If a multipage TIFF file is passed to pdfbeads, warn user that
+      only the first image will be processed.
+
+    * TIFF files with an embedded EXIF block were incorrectly processed
+      by ImageInspector.

data/bin/pdfbeads

@@ -45,6 +45,7 @@ pdfargs  = Hash[
   :meta           => nil
 ]
 pageargs = Hash[
+  :threshold       => 1,
   :maxcolors       => 4,
   :st_resolution   => 0,
   :bg_resolution   => 300,
@@ -108,13 +109,22 @@ OptionParser.new() do |opts|
                 "Generate one shared JBIG2 dictionary per NUM pages.",
                 "This option is only applied when JBIG2 compression",
                 "is used. Default value is #{pageargs[:pages_per_dict]}") do |p|
-    pageargs[:pages_per_dict] = p.to_i
+    pval = p.to_i
+    pageargs[:pages_per_dict] = pval if ( pval >= 0 )
   end
   opts.on("-r", "--force-resolution DPI",
                 "Set resolution for foreground mask images to the",
                 "specified value (in pixels per inch). Note that the",
-                "image is not actually resampled.") do |r|
-    pageargs[:st_resolution] = r.to_f
+                "image is not actually resampled.") do |dpi|
+    pageargs[:st_resolution] = dpi.to_f
+  end
+  opts.on("-t", "--threshold VAL",
+                "Set binarization threshold for mixed images. Valid",
+                "values are between 1 and 255. 1 is used by default,",
+                "as the input files are assumed to be preprocessed",
+                "with ScanTailor (http://scantailor.sourceforge.net)") do |t|
+    tval = t.to_i
+    pageargs[:threshold] = tval if ( (1..255).include? tval )
   end
   opts.on("-x", "--max-colors NUM",
                 "If pdfbeads finds an indexed file with NUM or",
@@ -123,7 +133,8 @@ OptionParser.new() do |opts|
                 "PDF page mask. Otherwise the file is treated just",
                 "like a normal greyscale or color image. Default",
                 "value is #{pageargs[:maxcolors]}") do |num|
-    pageargs[:maxcolors] = num.to_i
+    cval = num.to_i
+    pageargs[:maxcolors] = cval if ( (2..255).include? cval )
   end
 
   opts.separator "\n"

data/lib/pdfbeads/pdfbuilder.rb

@@ -281,7 +281,7 @@ class PDFBeads::PDFBuilder
       pages.addToDict( 'Count', page_objs.length )
       pages.addToDict( 'Kids', '[' << page_objs.map{|x| ref(x.getID).to_s}.join(' ') << ']' )
 
-      pkey = pidx + 1
+      pkey = (pidx + 1).to_s
       pkey = labels.getPageLabel( cur_range_id,pidx ) if labels != nil and labels.length > 0
       pages_by_num[pkey] = page.getID
       pidx += 1
@@ -547,10 +547,11 @@ class PDFBeads::PDFBuilder
     return nil if stencil.width.nil?
 
     width = stencil.width
-    height = stencil.height
+    height = rows_per_strip = stencil.height
     xres = stencil.x_dpi
     yres = stencil.y_dpi
-    rows_per_strip = stencil.tags[0x116][0]
+    rows_per_strip = stencil.tags[0x116][0] if
+      stencil.format.eql? :TIFF and stencil.tags.has_key? 0x116
 
     unless stencil.compression.eql? :CCITTFaxDecode and rows_per_strip >= height
       img = ImageList.new( path )

data/lib/pdfbeads/pdfpage.rb

@@ -55,6 +55,7 @@ class PDFBeads::PageDataProvider < Array
       ret   = 0
       force = @pageargs[:force_update]
       fres  = @pageargs[:st_resolution]
+      treshold = @pageargs[:threshold]
 
       map = Hash[
         :path => @name,
@@ -73,7 +74,6 @@ class PDFBeads::PageDataProvider < Array
 
       if insp.depth == 1
         @stencils << map
-        $stderr.puts( "Prepared data for processing #{@name}\n" )
         ret = 1
 
       else
@@ -85,7 +85,7 @@ class PDFBeads::PageDataProvider < Array
           img.class_type = PseudoClass
           ret = processIndexed( img,@pageargs[:maxcolors],force )
         end
-        ret = processMixed( img,force,map ) if ret == 0
+        ret = processMixed( img,treshold,force,map ) if ret == 0
         img.destroy!
 
         # Make sure there are no more RMagick objects
@@ -221,10 +221,10 @@ class PDFBeads::PageDataProvider < Array
       return ret
     end
 
-    def processMixed( img,force,map )
+    def processMixed( img,treshold,force,map )
       binpath = "#{@basename}.black.tiff"
       if not File.exists? binpath or force
-        im_copy = img.copy; bitonal = im_copy.threshold(1); im_copy.destroy!
+        im_copy = img.copy; bitonal = im_copy.threshold(QuantumRange/255*treshold); im_copy.destroy!
         bitonal.write( binpath ){
           self.format = 'TIFF'
           self.define( 'TIFF','rows-per-strip',img.rows )
@@ -237,6 +237,9 @@ class PDFBeads::PageDataProvider < Array
       bgpath = "#{@basename}.bg." << bgf.downcase
 
       if not File.exists? bgpath or force
+        if treshold > 1
+          bk = img.black_threshold(QuantumRange/255*treshold); img.destroy!; img = bk
+        end
         op = img.opaque( 'black','white' ); img.destroy!; img = op;
         if @pageargs[:force_grayscale]
           img.image_type = GrayscaleType

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: pdfbeads
 version: !ruby/object:Gem::Version 
-  hash: 19
+  hash: 17
   prerelease: false
   segments: 
   - 1
   - 0
-  - 2
-  version: 1.0.2
+  - 3
+  version: 1.0.3
 platform: ruby
 authors: 
 - Alexey Kryukov
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-11-13 00:00:00 +03:00
+date: 2010-11-16 00:00:00 +03:00
 default_executable: pdfbeads
 dependencies: []